Workup Of Solitary Pulmonary Nodules Research Articles

Abstract 2614: A deep learning model-based lung cancer risk assessment for incidental pulmonary nodules

Abstract Lung cancer is the leading cause of cancer death among both men and women. The solitary pulmonary nodule (SPN) is frequently seen on radiographs and computed tomography (CT) and often provokes additional clinical and imaging activities as an SPN alerts possible early stage lung cancer. However, reliable diagnosis of malignant lung nodules in the workup of SPN is challenging, making it difficult for early stage cancer management to avoid morbidity due to malignant cancer, patient distress, and increased costs caused by more invasive and unwarranted procedures for benign cases. We developed a deep learning model based on convolutional neural networks (CNNs) to predict lung cancer risk for incidental SPN. The model can help better management of incidental lung cancer by providing a reliable characterization of SPNs. Deep learning models currently are applied to nodule detection in low-dose CT scans of lung cancer screening for at-risk population. Our work aims to investigate whether deep learning can differentiate benign from malignant incidental SPN during normal dose CT exams, where the number of patients with SPN is an order more than that of lung screening population. We collected an incidental SPN dataset containing 139 CT scans to generate the nodule malignancy prediction model using 3D CNN. This dataset was collected from either contrast or non-contrast CT scans with regular doses. All 139 patients went through surgeries to remove the tumors. CT images were collected within one year before the surgery. 90 cases are malignant and the rest are benign. Ground truth labels were obtained from biopsies. Data were preprocessed by resampling, normalization, and cropping to unique volume around the SPN. The radiologists annotated the SPN location. Since the two nodule classes are imbalanced, we did online data augmentation to increase the variety of lung nodule images and balance the two classes. We used 80% of the data for training and 20% for testing. The deep learning structure adapted is a 3D Resnet with 68 layers and 33M parameters. The area under the receiving operating characteristics curve (AUC) of the prediction result was 0.81 while the accuracy was 79.6%. Applying GradCam to visualize important regions in CT scans contributing to the final predictions, we found that our trained ResNet model focuses on meaningful areas in lung nodules and detects malignant SPNs in most cases. Our preliminary results shows the feasibility of using deep learning to predict incidental lung nodules and improve diagnostic speed and accuracy. Citation Format: Pengyu Yuan, Tiancheng He, Hien Nguyen, Stephen T. Wong. A deep learning model-based lung cancer risk assessment for incidental pulmonary nodules [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2021; 2021 Apr 10-15 and May 17-21. Philadelphia (PA): AACR; Cancer Res 2021;81(13_Suppl):Abstract nr 2614.

Perspectives on Managing Solitary Pulmonary Nodules: A Survey of Primary Care Physicians

Primary care physicians (PCPs) may be involved in the evaluation of solitary pulmonary nodules (SPNs) detected through lung cancer screening. Little is known about their perspectives on the management or the referral of SPN. Using the American Medical Association's Physician Masterfile, we randomly surveyed 1384 PCPs between January and October 2015 with an 18% response rate. A subset analysis was performed on SPN management and referral practices of PCP. These results and those relating to practice characteristics were compared between family practice and internal medicine physicians. Responders and nonresponders did not differ by demographic characteristics. A total of 137 (55.5%) PCPs reported feeling confident in managing the workup of imaging-detected SPN. However, only 53 PCPs (21.3%) were inclined to manage the evaluation and follow-up of SPN. There was no significant difference between family practice and internal medicine physicians with regard to years in practice, size of practice, or referral to specialists. Family practitioners and internists similarly disagreed or were neutral to self-managing SPN (P = 0.60). Internists were twice as likely to express confidence as family practitioners (odds ratio 1.95, 95% confidence interval 1.09-3.48). Among all PCPs, 75.4% would refer management of these patients to a pulmonologist, 28.9% to a surgeon, and 24.2% to an oncologist. Confidence did not predict lung cancer screening practices. Although more than half of PCPs expressed confidence in the workup of SPN, most preferred referral to specialists. Additional research is needed to understand barriers to PCP management of incidental SPN in the effort to facilitate lung cancer screening.

What Is the Clinical Value of PET/CT in the Diagnosis of Pulmonary Nodules?

The noninvasive diagnostic workup of solitary pulmonary nodules (SPNs) continues to be a challenge for radiologists and nuclear medicine physicians. Morphological evaluation is useful to differentiate between benign and malignant SPNs, but there is a considerable overlap between the benign and the malignant features, resulting in a large fraction of morphologically indeterminate SPNs. Integrated PET/CT with the glucose analogue 18F-fluorodeoxyglucose (FDG PET/CT) can simultaneously evaluate morphological characteristics, anatomic location and metabolic status of SPNs. FDG PET/CT has been shown to result in an overall improved accuracy for the detection of malignant SPNs. In addition, it is the most accurate technique for the staging of malignant SPNs. On the other hand, there are many causes for false positive or false negative FDG PET/CTs. Therefore, FDG PET/CT cannot replace histological evaluation of SPNs, but can be clinically helpful in specific subgroups of patients with SPNs. The goal of this review is to provide an overview of the literature on PET/CT imaging in SPNs and to describe several clinical scenarios for the use of FDG PET/CT in SPNs.

Role of Positron Emission Tomography in the Diagnostic Workup of Solitary Pulmonary Nodule

Role of Positron Emission Tomography in the Diagnostic Workup of Solitary Pulmonary Nodule

Role of Positron Emission Tomography in the Diagnostic Workup of Solitary Pulmonary Nodule

Role of Positron Emission Tomography in the Diagnostic Workup of Solitary Pulmonary Nodule

Value of flexible bronchoscopy in the pre-operative work-up of solitary pulmonary nodules

The diagnostic value of flexible bronchoscopy in the pre-operative work-up of solitary pulmonary nodules (SPN) is still under debate among pneumologists, radiologists and thoracic surgeons. In a prospective observational manner, flexible bronchoscopy was routinely performed in 225 patients with SPN of unknown origin. Of the 225 patients, 80.5% had lung cancer, 7.6% had metastasis of an extrapulmonary primary tumour and 12% had benign aetiology. Unsuspected endobronchial involvement was found in 4.4% of all 225 patients (or in 5.5% of patients with lung cancer). In addition, flexible bronchoscopy clarified the underlying aetiology in 41% of the cases. The bronchoscopic biopsy results from the SPN were positive in 84 (46.5%) patients with lung cancer. Surgery was cancelled due to the results of flexible bronchoscopy in four cases (involvement of the right main bronchus (impaired pulmonary function did not allow pneumonectomy) n=1, small cell lung cancer n=1, bacterial pneumonia n=2), and the surgical strategy had to be modified to bilobectomy in one patient. Flexible bronchoscopy changed the planned surgical approach in five cases substantially. These results suggest that routine flexible bronchoscopy should be included in the regular pre-operative work-up of patients with SPN.

Solitary pulmonary nodule: A diagnostic algorithm in the light of current imaging technique

The solitary pulmonary nodule (SPN) is frequently seen on chest radiographs and computed tomography (CT). The finding of a SPN usually provokes a flurry of clinical and imaging activity as an SPN in at-risk population is an alert signal of possible lung cancer. The frequency of malignant nodules in a given population is variable and depends on the endemicity of granulomatous disease. The percentage of malignant nodules also rises when dealing with at-risk population. The problem is compounded by the fact that with the present generation of CT scanners, 1–2 mm nodules are discovered in approximately half of the smokers aged 50 years or older scanned. A variety of management approaches are applied in the work-up of SPN often requiring evaluation over a long period of time to establish a benign or malignant diagnosis. Comparison with previous imaging studies and morphologic evaluation of the size, margins, and internal characteristics are usually the first step in the evaluation of these nodules. It is often necessary to use additional imaging techniques and occasionally invasive procedures such a percutaneous needle lung or a surgical biopsy. Until recently, the guidelines for follow-up of indeterminate noncalcified nodules detected on nonscreening CT was a minimum of 2 years. However, during the past few years due to further refinements in CT technology and better understanding of tumor behavior, it has prompted a revision of the guidelines of the follow-up of small indeterminate nodules. These guidelines have been endorsed by the Fleischner Society.

Combined Contrast-Enhanced Computed Tomography and 18-Fluoro-2-Deoxy- d-Glucose-Positron Emission Tomography in the Diagnosis and Staging of Non-small Cell Lung Cancer

We present the current optimal uses and limitations of positron emission tomography/computed tomography (PET/CT) as it relates to the diagnosis and staging of non-small cell lung cancer (NSCLC). PET/CT demonstrates increased accuracy in the workup of solitary pulmonary nodules for malignancy compared with CT alone, and we discuss its benefits and limitations. We review pitfalls in measured standardized uptake values of lung lesions caused by respiratory artifacts, the lower sensitivity for detection of small lung nodules on non-breath-hold CT, and the benefits of obtaining an additional diagnostic CT for the maximum sensitivity of lung nodule detection. There are limitations of quantitatively comparing separate PET/CT examinations from different facilities with standardized uptake values. As for staging, we describe how PET/CT supplements clinical tumor-nodes-metastases (ie, TNM) staging, as well as mediastinoscopy, endobronchial ultrasound, and endoscopic ultrasound, which are the gold standard pathologic staging methods. We touch on the 7th edition TNM staging system based on the work by the International Association for the Study of Lung Cancer, an anatomically based staging method.